INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 billboards

-0.70

 Springfield

-0.70

aucus

-0.68

 Americ

-0.68

rican

-0.68

 Polk

-0.68

 deposition

-0.67

 millenn

-0.67

 Amar

-0.67

 Nieto

-0.67

POSITIVE LOGITS

ultimate

0.98

ubuntu

0.94

stress

0.89

null

0.88

exper

0.87

isSpecialOrderable

0.87

crit

0.85

overs

0.84

strings

0.81

powers

0.80

Activations Density 0.000%

No Known Activations

This feature has no known activations.